Gemma 4 Technical Report
Paper • 2607.02770 • Published • 79
AI & ML interests
Open science and open source
osanseviero
authored a
paper about 2 months ago
osanseviero
submitted a
paper to Daily Papers about 2 months ago
eienmojiki
posted an update 2 months ago
Post
278
Hi everyone,
I've created a Gradio space for embedding and extracting invisible watermarks in images:
👉 eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
I've created a Gradio space for embedding and extracting invisible watermarks in images:
👉 eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
woojun-jung
authored a
paper 4 months ago
minwoosun
authored a
paper 5 months ago
jorgemunozl
posted an update 7 months ago
Post
507
just published a short article about something that bit me hard while porting PI05’s subtask prediction to PyTorch: left vs right alignment in transformer padding.
turns out JAX (what Physical Intelligence used) and Hugging Face use opposite padding conventions — and if you don’t catch it, your model silently produces nonsense instead of crashing. no NaN, no error, just garbled subtasks 🤡
i walk through the full tensor pipeline — images → embeddings → pad masks → attention masks → position IDs — and show exactly where the mismatch corrupts everything. also included the implementation file with the fix.
if you’ve ever ported a model between frameworks or messed with custom attention patterns, i think you will enjoy it
turns out JAX (what Physical Intelligence used) and Hugging Face use opposite padding conventions — and if you don’t catch it, your model silently produces nonsense instead of crashing. no NaN, no error, just garbled subtasks 🤡
i walk through the full tensor pipeline — images → embeddings → pad masks → attention masks → position IDs — and show exactly where the mismatch corrupts everything. also included the implementation file with the fix.
if you’ve ever ported a model between frameworks or messed with custom attention patterns, i think you will enjoy it
- 1 reply
woojun-jung
authored a
paper 9 months ago
himanshubeniwal
authored 6
papers 11 months ago
Cross-lingual Editing in Multilingual Language Models
Paper • 2401.10521 • Published • 2
Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Models
Paper • 2402.11997 • Published • 1
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs
Paper • 2502.16901 • Published
COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing
Paper • 2503.21670 • Published
PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
Paper • 2504.04377 • Published • 1
COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework
Paper • 2408.03125 • Published
minwoosun
authored a
paper 11 months ago
osanseviero
authored a
paper 11 months ago
BrigitteTousi
posted an update about 1 year ago
Post
1340
On Wednesday, August 13 at 11am EDT, join @clem for a no bullshit AMA on Discord. Prep all your HF questions and meet us there! 🤗☄️⚡️
https://discord.com/invite/6r5TEXyk?event=1404451892179763311
https://discord.com/invite/6r5TEXyk?event=1404451892179763311
1024m
authored a
paper about 1 year ago
BrigitteTousi
posted an update about 1 year ago
Post
699
New interactive viz from AI World showing OpenAI's new open model gpt-oss-120b breaking into the top 50 most liked models of all time on the Hub in under a day! ☄️☄️☄️
1024m
authored a
paper about 1 year ago
BrigitteTousi
posted an update about 1 year ago
Post
711
This is what Hugging Face is all about. We want everyone, hobbyists, researchers and industry alike, to be able to contribute to AI because everyone is affected by it. Kudos to HF's @irenesolaiman for spreading the word!🔥🤗